Stephan Günnemann is a Professor at the Department of Informatics, Technical University of Munich. He acquired his doctoral degree in 2012 at RWTH Aachen University in the field of computer science. From 2012 to 2015 he was an associate of Carnegie Mellon University, USA; initially as a postdoctoral fellow and later as a senior researcher. Stephan Günnemann has been a visiting researcher at Simon Fraser University, Canada, and a research scientist at the Research & Technology Center of Siemens AG. His research interests include efficient data mining and machine learning techniques for high-dimensional, temporal, and network data.

AG 1, AG 2, AG 3, AG 4, AG 5, SWS, RG1, MMCI   Info

Public Audience

English

60 Minutes

Saarbrücken

Graph data representing complex interactions between instances is ubiquitous across many application domains. Social networks of interacting users; e-commerce systems of related products, users, and sellers; document citation graphs; or functional brain networks are only a few examples. With the mere size of these graphs being one big challenge, a further key limiting factor for analytics is the data's quality itself: the collected graphs are rarely clean but often noisy, prone to corruptions, and vulnerable to attacks. In this talk, I will present two data mining principles that tackle both of these challenges: (i) Robust spectral clustering in the presence of corrupted graphs, and (ii) collective classification in heterogeneous graphs for fraud detection. For both tasks, I will present the underlying modeling principles and I will sketch solutions how to derive efficient and highly scalable learning algorithms.

Petra Schaaf

5000

--email hidden

passcode not visible

logged in users only